Noise-induced self-supervised hybrid UNet transformer for ischemic stroke segmentation with limited data annotations

Abstract We extend the Hybrid Unet Transformer (HUT) foundation model, which combines the advantages of the CNN and Transformer architectures with a noisy self-supervised approach, and demonstrate it in an ischemic stroke lesion segmentation task. We introduce a self-supervised approach using a nois...

Descripció completa

Dades bibliogràfiques

Autors principals:	Wei Kwek Soh, Jagath C. Rajapakse
Format:	Artigo
Idioma:	Inglês
Publicat:	Nature Portfolio 2025-06-01
Col·lecció:	Scientific Reports
Matèries:	Self-supervised Limited annotation Ischemic stroke segmentation Noise regularisation Small dataset
Accés en línia:	https://doi.org/10.1038/s41598-025-04819-2
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!